© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 45221
    Prev
    Next
    INDEX
    Explanations

    prescribed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prescribing
    -1.20
     prescribed
    -1.20
     prescribe
    -1.20
    MigrationBuilder
    -0.94
     mortality
    -0.92
    specified
    -0.86
     specified
    -0.85
     prescribes
    -0.85
     enclosed
    -0.85
    EndInit
    -0.84
    POSITIVE LOGITS
     Shi
    0.50
     Tor
    0.49
     Tar
    0.48
     a
    0.48
     Do
    0.45
     PH
    0.44
    ض
    0.44
     BeautifulSoup
    0.43
    jsoup
    0.43
     by
    0.42
    Activations Density 0.040%

    No Known Activations